:::

只用CPU跑「小型」語言模型可行嗎? / Is Running "Small" Language Models on CPUs Only Feasible?

布丁布丁吃布丁

只用CPU跑「小型」語言模型可行嗎? / Is Running "Small" Language Models on CPUs Only Feasible?

2025-0121-211755.png

很多人都說跑大型語言模型需要很高級的GPU,其實相對於門檻較高的大型語言模型,小型語言模型也一直在如火如荼地發展。最近我嘗試用12核CPU跟32GB的RAM來跑Gemma2:2B,意外地很順利呢。

Many people say that running large language models requires high-end GPUs. However, relative to the higher barrier to entry of large language models, small language models have also been developing rapidly. Recently, I experimented with running Gemma2:2B using a 12-core CPU and 32GB of RAM, and it went surprisingly smoothly.

(more...)

RAG應用方案:SeaSalt.AI的SeaMeet、SeaChat / RAG Application Solutions: SeaSalt.AI's SeaMeet and SeaChat

布丁布丁吃布丁

RAG應用方案:SeaSalt.AI的SeaMeet、SeaChat / RAG Application Solutions: SeaSalt.AI's SeaMeet and SeaChat

2025-0121-170841.png

我最近試用了SeaSalt公司底下的SeaMeet跟SeaChat,前者可以自動記錄並摘要 Google Meet會議內容,後者則是簡單建立聊天機器人。這篇就是我報告投影片的彙整,供大家參考。

(more...)

量表Cronbach's Alpha內部信度分析計算器:以Colab實作 / Cronbach's Alpha Internal Consistency Reliability Calculator: Implementation Using Colab

布丁布丁吃布丁

量表Cronbach's Alpha內部信度分析計算器:以Colab實作 / Cronbach's Alpha Internal Consistency Reliability Calculator: Implementation Using Colab

2024-1221-224518.png

我開發了一份Colab筆記本「內部一致性信度分析:Cronbach's Alpha計算器」,方便大家分析量表的內部一致信信度Cronbach's Alpha。這份筆記本能夠分析整份量表的Cronbach's Alpha,也可以各別計算量表中各個構面(subscaler)的Alpha係數。同時計算器還會用逐一移除題目的方式,藉由指出移除後能夠提高Cronbach's Alpha的題目,讓研究者仔細檢視量表的設計是否有改善空間。

I developed a Colab notebook titled "Internal Consistency Reliability Analysis: Cronbach's Alpha Calculator" to facilitate the analysis of a scale's internal consistency reliability using Cronbach's alpha. This notebook can analyze the Cronbach's alpha for the entire scale, as well as calculate the alpha coefficient for individual subscales. The calculator also performs item-level analysis, identifying items whose removal would increase Cronbach's alpha, allowing researchers to carefully examine and potentially improve the scale's design.

(more...)

雜談:怎麽讓AI能根據我的雲端硬碟回答問題 / TALK: How Can I Enable AI to Answer Questions Based on My Cloud Storage?

布丁布丁吃布丁

雜談:怎麽讓AI能根據我的雲端硬碟回答問題 / TALK: How Can I Enable AI to Answer Questions Based on My Cloud Storage?

2025-0121-143440.png

Nextcloud的AI應用程式不能處理中文,所以我自己用Langflow整合到Nextcloud,讓大型語言模型能夠根據我在雲端硬碟裡面的內容來回答問題。這篇就講一下大致上的做法。

(more...)

希希助教獻上新年祝福 / TA. Sissi's New Year Greetings

布丁布丁吃布丁

0 Comments

希希助教獻上新年祝福 / TA. Sissi's New Year Greetings

2024-1229-102005.png

蛇盤如意寓意著好運盤旋,事事如意。希望大家新的一年都有美好的開始!

(more...)

如何在Colab執行程式? / How to Run all Codes in Colab?

布丁布丁吃布丁

0 Comments

如何在Colab執行程式? / How to Run all Codes in Colab?

2024-1221-174101.png

使用Colab來進行資料分析時,必須要經過程式執行的動作,才能取得執行後的分析結果。以下就讓我來看看怎麽在Colab裡面執行程式。

When performing data analysis using Colab, you must execute the code to obtain the analysis results. Let's take a look at how to execute codes within Colab.

(more...)

雜談:總算把架設了Stable Diffusion WebUI Forge / TALK: Finally Set Up Stable Diffusion WebUI Forge

雜談:總算把架設了Stable Diffusion WebUI Forge / TALK: Finally Set Up Stable Diffusion WebUI Forge

2024-1223-160139.png

由於之前硬碟毀損,導致我用來做AI繪圖的Stable Diffusion環境全部消失。這次乾脆全部重來,用Stable Diffusion WebUI Forge重建整個繪圖環境吧。

(more...)